mlsanityData to 7 Oct 2026

Learned Neighbor Trust for Collaborative Deployment in Model-Agnostic Decentralized Learning

arXiv 2605.05009 ↗First posted 6 May 2026cs.LGcited by 0

Not on the map. Why?

Abstract (arXiv)

Many decentralized distillation methods are designed around training-time coordination, yet deploy each node in isolation even when more capable neighbors remain available at inference time. This is an incomplete objective for settings such as IoT, where devices are heterogeneous, data is scarce and skewed, and a node's strongest neighbors may far exceed its own local capacity. We study how nodes should train so that their predictions compose well at deployment, and how each node should learn whom to trust. Under a server-free, model-agnostic protocol where nodes exchange only queries and soft predictions, we propose Learned Neighbor Trust (LNTrust) wherein each node learns a compact trust function over its neighborhood from local validation evidence. This trust function gates auxiliary distillation during training and defines a deployment ensemble at inference, so that collaboration learned during training transfers directly to deployment. Across datasets and topologies, LNTrust improves deployed accuracy over the strongest output-only baseline by large margins while using significantly less communication than previous methods.

Key facts. No citing papers in the map yet (data through 7 Oct 2026). Builds on 22 of its 33 references that are in the map. First posted on arXiv 6 May 2026.

Builds on

22 of 33 references.

References · 22

  1. 2016Communication-Efficient Learning of Deep Networks from Decentralized Datacited by 7,592
  2. 2019Advances and Open Problems in Federated Learningcited by 3,021
  3. 2018Federated Optimization in Heterogeneous Networkscited by 2,971
  4. 2021Model-Contrastive Federated Learningcited by 762
  5. 2020Ensemble Distillation for Robust Model Fusion in Federated Learningcited by 678
  6. 2020Ditto: Fair and Robust Federated Learning Through Personalizationcited by 665
  7. 2017Deep Mutual Learningcited by 621
  8. 2020Personalized Federated Learning with Moreau Envelopescited by 612
  9. 2017Can Decentralized Algorithms Outperform Centralized Algorithms? A Case Study for Decentralized Parallel Stochastic Gradient Descentcited by 496
  10. 2017Mean teachers are better role models: Weight-averaged consistency targets improve semi-supervised deep learning resultscited by 470
  11. 2019FedMD: Heterogenous Federated Learning via Model Distillationcited by 454
  12. 2020Personalized Federated Learning with First Order Model Optimizationcited by 201
10 more
  1. 2020FedBE: Making Bayesian Model Ensemble Applicable to Federated Learningcited by 176
  2. 2020Distillation-Based Semi-Supervised Federated Learning for Communication-Efficient Collaborative Training with Non-IID Private Datacited by 125
  3. 2021Personalized Federated Learning through Local Memorizationcited by 57
  4. 2022Test-Time Robust Personalization for Federated Learningcited by 39
  5. 2023Adaptive Test-Time Personalization for Federated Learningcited by 23
  6. 2024Overcoming Data and Model Heterogeneities in Decentralized Federated Learning via Synthetic Anchorscited by 21
  7. 2024Revisiting Ensembling in One-Shot Federated Learningcited by 13
  8. 2023Homogenizing Non-IID datasets via In-Distribution Knowledge Distillation for Decentralized Learningcited by 3
  9. 2024FedPAE: Peer-Adaptive Ensemble Learning for Asynchronous and Model-Heterogeneous Federated Learningcited by 1
  10. 2026Federated Inference: Toward Privacy-Preserving Collaborative and Incentivized Model Servingcited by 1

Built on by

Not cited yet.